Skip to main content
Glama

Chembl Mechanism

chembl_mechanism
Read-onlyIdempotent

Mechanism of action of a drug, from its NAME (or a ChEMBL molecule ID). Answers "how does metformin work", "what is the mechanism of action of X", "what does X inhibit", "what target does X act on", "X mode of action", "is X an agonist or an antagonist", "X molecular target". Resolves the drug name to every matching ChEMBL molecule form, the base compound together with its salts, hydrochlorides, mesylates and branded formulations, and searches all of them at once, so a drug whose pharmacology is curated on the salt form still resolves. Returns, per mechanism: action_type (INHIBITOR, AGONIST, ANTAGONIST, BLOCKER, MODULATOR, ...), the mechanism_of_action sentence (e.g. "Mitochondrial complex I (NADH dehydrogenase) inhibitor"), the molecular target with its ChEMBL target ID, target name and organism, the exact molecule form the mechanism is recorded on with its preferred name, max clinical phase, curator mechanism/selectivity comments, and PubMed references. Also lists every molecule ID searched, so an empty result is interpretable. Curated pharmacology from ChEMBL (EMBL-EBI). Reach for this for pharmacology, mode of action, drug-target identification, and any "how does this drug work" question.

Example tool call

This call uses example arguments supplied in the tool’s input schema.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "drug": "metformin"
    },
    "name": "chembl_mechanism"
  }
}

Input Schema

NameRequiredDescriptionDefault
qNoAlias for drug.
drugNoDrug name, e.g. "metformin", "imatinib", "aspirin". Brand, generic, or salt names all work.
nameNoAlias for drug.
limitNoMax mechanisms returned, 1-200 (default 50).
queryNoAlias for drug.
chembl_idNoAlias for molecule_chembl_id.
candidatesNoHow many name-matched molecule forms to search across, 1-25 (default 10). Higher catches obscure salt forms.
molecule_chembl_idNoExact ChEMBL molecule ID instead of a name, e.g. "CHEMBL1431". Salt forms of this molecule are included automatically.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.3/5.0
Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Beyond the annotations (readOnly, idempotent, openWorld, non-destructive), it discloses important behavior the annotations cannot: name resolution expands to base compound plus salts, hydrochlorides, mesylates and branded forms and searches all at once, and it returns every molecule ID searched so an empty result is interpretable. It also pre-describes the per-mechanism return fields (action_type, mechanism sentence, target + ChEMBL target ID, organism, max phase, curator comments, PubMed refs).

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The purpose is front-loaded and there is no filler, but the description is one long block that lists seven near-duplicate example phrasings ("what does X inhibit", "X mode of action", "X molecular target") and then a full field-by-field return list. Several of those clauses restate the same point and could be consolidated.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a search tool with no output schema and full schema coverage of its 8 parameters, the description covers everything an agent needs: what it accepts, how names are expanded across salt/brand forms, what fields come back, and how to read an empty result. Nothing material is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so drug, molecule_chembl_id, limit and candidates are already documented in the schema, including the salt-form inclusion for IDs and the purpose of candidates. The description reinforces the name-vs-ID input path but adds no new semantics such as accepted name formats beyond what the schema states.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description opens with a precise verb and resource ("Mechanism of action of a drug") and immediately enumerates the concrete questions it answers ("how does metformin work", "what does X inhibit", "is X an agonist or an antagonist"). That makes it clearly separable from sibling pharmacology tools such as molecule, activities, or chembl_target without opening any schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

It gives explicit usage context: "Reach for this for pharmacology, mode of action, drug-target identification, and any 'how does this drug work' question," plus example user phrasings. It does not name an alternative tool or state when NOT to use it, so it stops short of full routing guidance.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.